Towards Efficient Selection of Activity Trajectories based on Diversity and Coverage
Authors: Chengcheng Yang, Lisi Chen, Hao Wang, Shuo Shang689-696
AAAI 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experiments on two real-world datasets show that our proposal significantly outperforms state-of-the-art baselines. ... We conduct experiments on two real-world datasets. The experimental results demonstrate the efficiency and effectiveness of our proposal. |
| Researcher Affiliation | Academia | 1East China Normal University 2University of Electronic Science and Technology of China 3Nanjing University of Information Science and Technology |
| Pseudocode | Yes | Algorithm 1 presents the implementation of our method. |
| Open Source Code | No | The paper does not provide any concrete access information (e.g., repository links, explicit statements of code release) for the source code of the described methodology. |
| Open Datasets | Yes | We experimented on two real-world datasets: TDrive [Yuan et al. 2011] and NYCTL [Donovan and Work 2015]. |
| Dataset Splits | Yes | In addition, 30%/10%/60% of the ground truth data was used for training/parameter tuning/testing. |
| Hardware Specification | Yes | We conducted experiments on a workstation powered by Intel Xeon Gold-6148 CPU on Linux (Ubuntu 16.04), having a Nvidia Titan Xp GPU. |
| Software Dependencies | No | The paper mentions "Linux (Ubuntu 16.04)" as the operating system, but does not provide specific version numbers for any other software dependencies, libraries, or frameworks used in the experiments. |
| Experiment Setup | Yes | The sampling size η was set as 10. For the Da ATS problem, we used the whole dataset and set the similarity threshold θ as 0.8. We randomly sampled 100 square-shape regions as the explored regions. By default, we set the region size as 0.01 of the city size and selected a subset of size 100. ... We tuned d using grid search and set d = 512. ... For self-attention, we searched hyperparameters in a wide range and found that d = 600 and u = 5 worked best. ... We tuned K with grid search and set K = 9 as it worked best. ... we divided the space into 200m 200m grid cells and set the maximum number of groups γ in each grid cell as 6. |